Raw model output on the native 0.25° grid — no MOS, no bias correction, no post-processing. Scores understate operational forecast quality. Read the fairness statement →

CastCheck methodology v0.2 · data through 2026-08-30

KLAS — Las Vegas Harry Reid

36.0719, -115.1634 · 664 m· standard offset UTC-8 h · truth product CLILAS

These pages are always bilinear interpolation, the headline method. The nearest-node variant, and every other window/initialization/interpolation/variable combination, is published on each permanent link below — follow any number.

Daily maximum temperature — MAE °F

the last 90 days, 12Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 4.94-4.69 · n=29 4.80-4.64 · n=28 4.93-4.93 · n=27 5.18-5.02 · n=26 5.62-5.24 · n=24 5.73-5.23 · n=24 6.52-5.77 · n=23 6.98-6.46 · n=22 7.54-7.23 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmax
Aurora (GFS init)aurora_gfs 6.44-6.44 · n=2 6.07-6.07 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmax
Aurora (IFS init)aurora_ifs 3.83-3.83 · n=2 3.42-3.42 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (GFS init)fourcastnet_gfs 5.66-5.66 · n=2 5.11-5.11 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (IFS init)fourcastnet_ifs 5.51-5.51 · n=2 3.23-3.23 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmax
NCEP GFSgfs 5.22-4.64 · n=29 4.29-3.47 · n=28 4.38-3.43 · n=27 4.28-2.88 · n=26 4.51-2.53 · n=25 5.61-4.17 · n=24 6.80-4.09 · n=23 7.05-3.89 · n=22 6.55-3.78 · n=21 NCEP GFS MAE by lead day 1 to 9, tmax
GraphCast (GFS init)graphcast_gfs 6.51-6.51 · n=2 8.51-8.51 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmax
GraphCast (IFS init)graphcast_ifs 5.77-5.65 · n=27 6.14-6.11 · n=26 6.43-6.43 · n=25 7.06-6.82 · n=25 7.64-7.28 · n=25 8.09-7.61 · n=24 8.95-8.65 · n=23 9.30-8.62 · n=22 8.76-8.26 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmax
ECMWF IFS HRESifs_hres 4.69-4.34 · n=24 3.53-2.47 · n=22 3.37-2.24 · n=22 3.70-2.56 · n=21 4.10-3.27 · n=20 4.04-3.81 · n=19 4.84-4.21 · n=17 4.73-3.35 · n=17 5.57-4.67 · n=14 ECMWF IFS HRES MAE by lead day 1 to 9, tmax
Pangu-Weather (GFS init)pangu_gfs 5.64-5.64 · n=2 5.57-5.57 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmax
Pangu-Weather (IFS init)pangu_ifs 5.31-5.31 · n=2 4.68-4.68 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmax
Persistence (baseline)persistence 2.94-0.01 · n=90 4.07-0.13 · n=90 4.94-0.34 · n=90 5.52-0.70 · n=90 6.22-1.00 · n=90 6.80-1.29 · n=90 6.83-1.48 · n=90 6.76-1.64 · n=90 7.14-1.81 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmax

Up to 2 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

+ model too warm · − model too cold · bias interval includes zero · ★ lowest MAE · = not distinguishable from the leader · ▼ significantly worse · n < 30 greyed and unranked · CI is a 95 % moving-block bootstrap interval.

Daily minimum temperature — MAE °F

the last 90 days, 12Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 5.05-4.98 · n=29 5.10-5.01 · n=28 5.05-4.86 · n=27 4.82-4.66 · n=26 4.96-4.57 · n=24 5.45-5.05 · n=24 5.46-5.05 · n=23 5.43-5.18 · n=22 6.28-6.05 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmin
Aurora (GFS init)aurora_gfs 7.33-7.33 · n=2 8.46-8.46 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmin
Aurora (IFS init)aurora_ifs 5.87-5.87 · n=2 7.08-7.08 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (GFS init)fourcastnet_gfs 5.69-5.69 · n=2 6.48-6.48 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (IFS init)fourcastnet_ifs 5.68-5.68 · n=2 6.66-6.66 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmin
NCEP GFSgfs 3.32-1.52 · n=29 3.26-0.71 · n=28 3.60-0.12 · n=27 3.87-0.34 · n=26 3.61+0.25 · n=25 4.06-0.05 · n=24 4.71-1.37 · n=23 5.18-0.77 · n=22 5.08-0.22 · n=21 NCEP GFS MAE by lead day 1 to 9, tmin
GraphCast (GFS init)graphcast_gfs 7.16-7.16 · n=2 8.06-8.06 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmin
GraphCast (IFS init)graphcast_ifs 3.54-3.50 · n=27 3.48-3.42 · n=26 3.60-3.51 · n=25 3.79-3.50 · n=25 4.37-3.81 · n=25 4.84-4.33 · n=24 5.70-4.28 · n=23 5.41-4.71 · n=22 6.66-5.57 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmin
ECMWF IFS HRESifs_hres 3.58-2.96 · n=24 3.71-3.16 · n=22 3.84-2.93 · n=22 4.03-2.67 · n=21 4.36-2.67 · n=20 4.66-2.98 · n=19 4.82-3.55 · n=17 5.07-4.42 · n=17 6.05-5.84 · n=14 ECMWF IFS HRES MAE by lead day 1 to 9, tmin
Pangu-Weather (GFS init)pangu_gfs 4.87-4.87 · n=2 5.91-5.91 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmin
Pangu-Weather (IFS init)pangu_ifs 6.33-6.33 · n=2 8.40-8.40 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmin
Persistence (baseline)persistence 2.40-0.13 · n=90 3.82-0.31 · n=90 4.61-0.59 · n=90 5.34-0.92 · n=90 5.92-1.26 · n=90 6.34-1.54 · n=90 6.34-1.83 · n=90 6.52-2.03 · n=90 6.89-2.20 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmin

Up to 2 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

Month-by-month slices, model availability and the observed-truth table live on the canonical page: they do not depend on the window, initialization or interpolation selected here.

All scores as JSON scores_latest.csv daily_errors.csv.gz data & licences